Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1132
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by a number or reference to a specific location

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    218
    +0.10
    0.5%
    324
    +0.10
    0.4%
    649
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    324
    +0.10
    0.03
    29
    +0.10
    0.03
    171
    +0.09
    0.03
    Negative Logits
    \/
    -0.73
    abet
    -0.72
    etus
    -0.71
    ãĥī
    -0.69
    CTV
    -0.67
    juven
    -0.66
    uman
    -0.66
    iculture
    -0.60
    ript
    -0.60
    auga
    -0.60
    POSITIVE LOGITS
     intermedi
    0.85
    shaw
    0.78
     waivers
    0.75
    put
    0.74
     2021
    0.73
     2022
    0.73
    lace
    0.72
     2024
    0.72
    out
    0.72
    lines
    0.71
    Activations Density 0.044%

    No Known Activations